FRML-161 Refactor Preprocessing architecture to implement whitening #79
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Eve-ning
changed the title
Merged
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Major Changes
While this story is only to implement whitening, we opted to refactor it to improve flexibility such that it can handle per-dataset standard scaling, which is necessary to implement future preprocessing steps more easily.
Notably, we allow transforms to be mutated after the dataset has been constructed. Therefore, transforms that depend on the dataset, can fit on the dataset, then append itself onto the dataset, which is fitting for any scaling preprocessing step.
In our PR, we added
ImageStandardScaler, a flexible StandardScaler for images, with helper functions to deal with nested Images. It can fit onto the dataset after initialization, by sampling it then evaluating the stdev and mean. After, it is able to be fit into the augmentation transforms as a final step.